One Recipe, Many Harnesses: What Self-Evolution Encodes Across Languages and Models
Source
Siqi Yang, Qianlan Yang, Yu-Xiong Wang, Saurabh Pujar, Martin Hirzel
Author
Siqi Yang, Qianlan Yang, Yu-Xiong Wang, Saurabh Pujar, Martin Hirzel
Date
Terms in this piece · Glossary
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Why it matters
Anyone building self-improving AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → scaffolds learns which parts of a agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → generalize and which must be re-evolved per language ecosystem.
articleWhere Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM AgentsMichael Nguyen, Wei Chen Tan, Nurul Aisyah Hassan, Arvind Raman, Li Hua Lim, Ahmad Faiz Razak
articleThe Evolution of the Agent HarnessDan McAteer
articleBridging intent and execution in agentic systemswww.amazon.science